Skip to content
AI-grafen
Sign in
☰ Menu

The goal G Frontier Lab

Reproduce a paper

Read a research paper, state the hypothesis, implement the method, run ablations, and compare with the published results.

Knowledge nodes
43
From zero
about 35 h
Labs
6
See what you already know — no account

The diagnostic removes what you already know, so your path is usually much shorter.

What you can do afterwards

Labs along the way

You write the code. Tests you cannot see decide whether it holds up.

Lab: ablation — which component does the work?Ga sandbox · about 90 minLab: a neural network in pure NumPy — forward, backprop, gradient checkDa sandbox · about 75 minLab: dot product, norm and cosine similarityDin the browser · about 40 minLab: gradient descent from scratchDin the browser · about 50 minLab: matrix multiplication and one layer of a neural networkDin the browser · about 45 minLab: scaled dot-product attention with a causal maskDa sandbox · about 60 min

The whole path

Everything the goal builds on, grouped by level and in the order it builds on itself. Show on the map

AExplorer2 knowledge nodes
  1. Patterns and categories
  2. Sequences and precise instructions
BInvestigator6 knowledge nodes
  1. Data in everyday life
  2. Algorithmic thinking
  3. Rule-based systems and machine learning
  4. Source criticism and responsibility in AI use
  5. Training data, features and labels
  6. Classification: how a model sorts information
CBuilder9 knowledge nodes
  1. Functions and coordinate systems
  2. Programming logic — variables, conditions, loops
  3. Python — the basics
  4. Python — lists, loops and dictionaries
  5. Statistics — mean, median and spread
  6. Probability — the basics
  7. Linear regression: fitting a straight line to data
  8. Neural networks — the intuition
  9. Prompting — steering a language model
DAI developer17 knowledge nodes
  1. Derivatives and optimisation
  2. Loss functions
  3. Tokenisation
  4. Gradient descent
  5. Vectors
  6. Matrices and matrix multiplication
  7. Linear regression with several features
  8. Neural networks — the forward pass with matrices
  9. Backpropagation
  10. Embeddings — words as vectors
  11. Attention
  12. Overfitting and generalisation
  13. PyTorch — tensors and autograd
  14. Retrieval — finding the right text
  15. Training, validation and test
  16. Train a neural network in PyTorch
  17. Transformers — the architecture
EUniversity5 knowledge nodes
  1. Language models — training and generation
  2. Model evaluation
  3. RAG — retrieval-augmented generation
  4. Scientific method in AI
  5. Reproducibility
FAI engineering2 knowledge nodes
  1. Evals for language models and agents
  2. Reading and analysing research papers
GFrontier Lab2 knowledge nodes
  1. Ablation studies
  2. Reproducing a paper